© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110203
    Prev
    Next
    INDEX
    Explanations

    negativity or fiction

    np_max-act · gemini-2.0-flash

    The neuron triggers on mentions of violence (tokens like “viol,” “violent,” or “violence”), marking when violent content is referenced.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nod
    -0.06
    ALTH
    -0.06
    刚
    -0.06
    Dire
    -0.06
     　 　 　 　 　
    -0.06
     난
    -0.06
     theories
    -0.06
    -sheet
    -0.06
    .SimpleButton
    -0.06
     AMAZ
    -0.06
    POSITIVE LOGITS
    IData
    0.07
     afirm
    0.07
     Cumhurbaşkanı
    0.07
    -il
    0.07
    .savefig
    0.07
    .breakpoints
    0.07
     أع
    0.07
    _CB
    0.06
    lü
    0.06
     jedn
    0.06
    Activations Density 0.005%

    No Known Activations